Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,395 skills from 2,375 repositories · updated 3 minutes ago
49,395 skills
- dev-simplifycodeaholicguy/ai-devkitAI DevKit · Analyze and simplify existing implementations to reduce complexity, improve maintainability, and enhance scalability. Use when users ask to simplify code, reduce complexity, refactor for readability, clean up implementations, improve maintainability, reduce technical debt, or make code easier to understand.EngineeringNo warnings★ 1.7K↓ —
- founder-boardJakeschincariol/founder-skillYour board of directors. Puts a business idea in front of a three-member board, each a sub-agent reading the idea through one published framework: the Offers lens (from Alex Hormozi's $100M Offers), the Monopoly lens (from Peter Thiel's Zero to One) and the Product lens (from Walter Isaacson's biography of Steve Jobs). Each member scores the idea, names the risks that would kill it and votes fund, fund with conditions, or pass. Use when the user says "test my business idea", "would this work", "pressure-test this", "what would a board say", "is this a good business", or starts the founder pack on a new idea.TestingNo warnings★ 2.4K↓ —
- lma-facilityKlotzkette/claude-fuer-deutsches-rechtFür Deal-Kommandocenter — Corporate/M&A: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Corporate-Kanzlei. Route: lma-facility.OtherNo warnings★ 1.8K↓ —
- android-for-cars-parked-appsandroid/skillsAdapt existing Android video streaming apps, games, and web browsers to run as parked apps on Android Auto and Android Automotive OS. Covers manifest configuration, Google Play hardware feature declarations, compatibility mode, back navigation affordances, orientation and display continuity, controllable system bar insets, irregular display cutouts, driver distraction lifecycle handling, MediaSession playback restrictions with CarUxRestrictionsManager, background audio while driving, and browser sensitive data protection. Use this skill when migrating, building, or auditing parked apps for cars to meet Car App Quality guidelines. Don't use for media audio apps, templated Car App Library navigation, point of interest, internet of things, weather, or communication apps designed for use while driving.OfficialBrowserNo warnings★ 10.3K↓ —
- remote-from-slackcodeaholicguy/ai-devkitAI DevKit · Connect the current agent session to an available Slack channel bridge.OtherNo warnings★ 1.7K↓ —
- founder-brandJakeschincariol/founder-skillYour brand designer. Names the business (with the trademark, domain and handle checks to run before falling in love with a name), writes the voice, a one-line promise and a tagline, and briefs the look: colours, type, logo and the first things a customer sees, so they match the positioning the marketing director chose. Use when the user says "name my business", "brand this", "logo", "brand identity", "what should it look like", "tagline", or "brand voice".MarketingNo warnings★ 2.4K↓ —
- bmlehKlotzkette/claude-fuer-deutsches-rechtFür Legistik-Werkstatt — Allgemein: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 1.8K↓ —
- seabornsickn33/agentic-awesome-skillsSeaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.EngineeringNo warnings★ 49.1K↓ —
- astropysickn33/agentic-awesome-skillsAstropy is the core Python package for astronomy, providing essential functionality for astronomical research and data analysis.DataNo warnings★ 49.1K↓ —
- glance-canonical-layoutsandroid/skillsUse this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).OfficialMediaNo warnings★ 10.3K↓ —
- hypogenicK-Dense-AI/scientific-agent-skillsPlans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. Use for the `hypogenic` package, its task configs, hypothesis banks, or HypoBench datasets—not for manual hypothesis formulation or scientific validation.ScienceNo warnings★ 56K↓ —Also in 1 other repo
- dev-debugcodeaholicguy/ai-devkitAI DevKit · Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when users ask to debug bugs, investigate regressions, triage incidents, diagnose failing behavior, handle failing tests, analyze production incidents, investigate error spikes, or run root cause analysis (RCA).EngineeringNo warnings★ 1.7K↓ —
- scholar-evaluationK-Dense-AI/scientific-agent-skillsProvides qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls. Never use for ranking people or consequential decisions.ScienceNo warnings★ 56K↓ —
- review-richtlinieKlotzkette/claude-fuer-deutsches-rechtFür Prüfung: Internationaler Bezug und Schnittstellen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.EngineeringNo warnings★ 1.8K↓ —
- ressort-bmasKlotzkette/claude-fuer-deutsches-rechtFür Ressort-Heranführung BMAS: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 1.8K↓ —
- blog-decayAgriciDaniel/claude-blogCompare two Google Search Console page exports (current vs previous period) to flag pages whose clicks or impressions fell by a chosen threshold, with a triage hint (refresh, query shift, consolidate, prune). The 20% default is a screening heuristic, not proof of decay. Use for "/blog decay", "content decay", "QoQ decline", "refresh declining posts". Needs two GSC exports; not for diagnosing a single traffic drop live (blog-google) or rewriting posts (blog-rewrite).WritingNo warnings★ 2.6K↓ —
- shuorenhuaMrGeDiao/shuorenhua按用户要求审稿或去 AI 味，支持中英文；保留事实、术语与责任主体，支持只标问题。OtherNo warnings★ 2.4K↓ —
- create-websitewondelai/skillsGuided journey from a blank page to a live, high-converting website, built message-first, then design, then conversion. Orchestrates ten skills phase by phase - one-page-marketing, storybrand-messaging, made-to-stick, top-design, web-typography, refactoring-ui, ux-heuristics, cro-methodology, scorecard-marketing, steve-jobs-design-review - asking the user questions at every decision point and recording results in the project docs/ folder (POSITIONING.md, WEBSITE.md, CREATE-WEBSITE-PLAN.md) so the journey resumes across sessions. Use when the user wants to build a new website or landing page from scratch, turn a validated idea into a page that converts, or says 'build me a landing page for my SaaS'. Site already exists: use improve-website site-wide, conversion-optimization for one flow, or grow-website for traffic; building a software product, not a marketing site: create-app; no positioning yet: create-business first, or the positioning phase here. For one framework in isolation, invoke that skill directly.DesignNo warnings★ 2.6K↓ —Also in 2 other repos
- pydeseq2K-Dense-AI/scientific-agent-skillsPerforms bulk RNA-seq differential expression analysis with PyDESeq2, including count validation, formula designs, explicit contrasts, Wald tests, FDR correction, coefficient-matched LFC shrinkage, and result visualization. Use for PyDESeq2 or Python DESeq2 workflows with biological replicates.TestingNo warnings★ 56K↓ —Also in 1 other repo
- blog-brandAgriciDaniel/claude-blogEstablish durable brand and voice context for cross-skill consumption. Generates BRAND.md (audience, positioning, do/don't editorial rules, taboo phrases, competitor differentiation) and VOICE.md (existing persona JSON re-expressed as readable prose), both written to the project root. When present, the blog orchestrator loads these files, fenced as untrusted data, for write, rewrite, brief, outline, calendar, and strategy workflows. Pairs with blog-persona, which manages the structured persona JSON. Use when the user says "blog brand", "create brand context", "BRAND.md", "VOICE.md", "establish editorial brand". Not for learning a voice from existing posts (blog-style) or managing persona JSON (blog-persona).WritingNo warnings★ 2.6K↓ —
- torchdrugK-Dense-AI/scientific-agent-skillsBuilds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.ScienceNo warnings★ 56K↓ —Also in 1 other repo
- scientific-writingK-Dense-AI/scientific-agent-skillsDrafts, revises, and audits scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.ScienceNo warnings★ 56K↓ —
- sympysickn33/agentic-awesome-skillsSymPy is a Python library for symbolic mathematics that enables exact computation using mathematical symbols rather than numerical approximations.EngineeringNo warnings★ 49.1K↓ —
- commitpedrohcgs/claude-code-my-workflowCommit the current work — runs the quality, consistency and passport gates, branches off main if needed, stages specific files, and writes a commit whose subject states what is now true. Pushes and opens a pull request only with --pr or when the user asks; never merges — a merge happens only when the user explicitly says to merge. Use ONLY on explicit commit intent — user says "commit", "let's commit this", "open a PR", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Never force-pushes or skips hooks.EngineeringNo warnings★ 1.7K↓ —
spark-training-gotchas
wshobson/agents
OtherUpdated 2 days ago
From the author
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
Install
npx skills add wshobson/agents --skill spark-training-gotchas -a claude-code
Installs to .claude/skills/spark-training-gotchas/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsUses the networkLicence: MIT
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 89
Security85
Provenance95
Maintenance100
Licence100
Adoption71
Files (3)
- SKILL.md
- assets/preflight.sh
- references/gotcha-checks.md